Annie Surla

Annie Surla is a Developer Advocate Engineer at NVIDIA responsible for developing and presenting a wide range of deep learning software products. She comes with experience working in deep learning applications including vision and NLP. She holds a master’s degree in Engineering Management from Duke University.
Avatar photo

Posts by Annie Surla

Decorative image.
Agentic AI / Generative AI Aug 11, 2026

Route AI Agent Workloads Across Models with NVIDIA NeMo Switchyard

Building an AI agent does not end with choosing a single model. Each model has its own strengths, weaknesses, and cost profile, which can shift from one... 12 MIN READ
An illustration for NVIDIA Llama Nemotron Nano VL.
Agentic AI / Generative AI Jun 03, 2025

New NVIDIA Llama Nemotron Nano Vision Language Model Tops OCR Benchmark for Accuracy

Documents such as PDFs, graphs, charts, and dashboards are rich sources of data that, when extracted and organized, provide informative decision-making... 8 MIN READ
image of jensen avatar
Agentic AI / Generative AI May 23, 2025

An Easy Introduction to LLM Reasoning, AI Agents, and Test Time Scaling

Agents have been the primary drivers of applying large language models (LLMs) to solve complex problems. Since AutoGPT in 2023, various techniques have been... 10 MIN READ
Agentic AI / Generative AI Mar 06, 2025

How Using a Reranking Microservice Can Improve Accuracy and Costs of Information Retrieval

Applications requiring high-performance information retrieval span a wide range of domains, including search engines, knowledge management systems, AI agents,... 8 MIN READ
Agentic AI / Generative AI Dec 16, 2024

An Easy Introduction to Multimodal Retrieval-Augmented Generation for Video and Audio

Building a multimodal retrieval-augmented generation (RAG) system is challenging. The difficulty comes from capturing and indexing information from across... 12 MIN READ
Agentic AI / Generative AI Oct 28, 2024

An Introduction to Model Merging for LLMs

One challenge organizations face when customizing large language models (LLMs) is the need to run multiple experiments, which produces only one useful model.... 10 MIN READ